Filters








282,161 Hits in 4.6 sec

Non-Uniform Network Mapping and Localization

Wei Liu, Yanxi Yang, Wenqing Wang
2020 IEEE Access  
INDEX TERMS Hierarchical mapping, non-uniform network, SLAM  ...  Inspired by human positioning ability, we developed a non-uniform network mapping and localization algorithm (NU-SLAM) based on the complex network theory.  ...  Then a non-uniform network mapping algorithm is proposed to represent the environment.  ... 
doi:10.1109/access.2020.2987104 fatcat:2sddcjspirhbnb3okzthf55wtu

An efficient network on-chip architecture based on isolating local and non-local communications

Vahideh Akhlaghi, Mehdi Kamal, Ali Afzali-Kusha, Massoud Pedram
2015 Computers & electrical engineering  
It consists of two network layers which one layer is dedicated to the packets transmitted to near destinations and the other layer is used for the packets transmitted to far destinations.  ...  In this paper, a locality aware NoC communication architecture is proposed. The architecture may reduce the energy consumption and latency in MultiProcessor Systems on Chips (MPSoCs).  ...  The network was implemented using VHDL and simulated for different non-uniform traffic patterns (i.e., 50%, 60%, 70%, and 80%).  ... 
doi:10.1016/j.compeleceng.2014.12.002 fatcat:uc5uusm53bh2pp2mnwnoinvkri

An Efficient Network-on-Chip Architecture Based on Isolating Local and Non-Local Communications

Vahideh Akhlaghi, Mehdi Kamal, Ali Afzali-Kusha, Massoud Pedram
2013 Design, Automation & Test in Europe Conference & Exhibition (DATE), 2013  
It consists of two network layers which one layer is dedicated to the packets transmitted to near destinations and the other layer is used for the packets transmitted to far destinations.  ...  In this paper, a locality aware NoC communication architecture is proposed. The architecture may reduce the energy consumption and latency in MultiProcessor Systems on Chips (MPSoCs).  ...  The network was implemented using VHDL and simulated for different non-uniform traffic patterns (i.e., 50%, 60%, 70%, and 80%).  ... 
doi:10.7873/date.2013.082 dblp:conf/date/AkhlaghiKAP13 fatcat:bip54sbbejbppfjcafc44nbxne

Uniform bases at non-isolated points and maps [article]

Fucai Lin, Shou Lin
2011 arXiv   pre-print
at non-isolated points; (2)\ Open and closed maps preserve regular spaces with an uniform base at non-isolated points; (3)\ Spaces with an uniform base at non-isolated points don't satisfy the decomposition  ...  In this paper, the authors mainly discuss the images of spaces with an uniform base at non-isolated points, and obtain the following main results: (1)\ Perfect maps preserve spaces with an uniform base  ...  In this paper we shall consider the invariance of spaces with an uniform base at non-isolated points under perfect maps or closed and open maps.  ... 
arXiv:1106.4135v1 fatcat:bjmteidejfdvrluexfjfl6f5v4

Non-Uniform Cellular Automata [chapter]

Marifi Güler, Hürevren Kiliç
1993 ICANN '93  
A model called Non-uniform Cellular Automata (NCA) is introduced and its capability to do mapping and computation is studied.  ...  The suggested model is similar to the original Cellular Automata, with its local neighborhood property, but neighborhood definition of cells do change in space and time (non-uniform) depending on the input-output  ...  Abstract-A model called Non-uniform Cellular Automata (NCA) is introduced and its capability to do mapping and computation is studied.  ... 
doi:10.1007/978-1-4471-2063-6_171 fatcat:qqn23igx5rcwnp4gjy44hyyfom

A Global-Local Blur Disentangling Network for Dynamic Scene Deblurring

Xiaoguang Li, Feifan Yang, Jianglu Huang, Li Zhuo
2021 Applied Sciences  
Images captured in a real scene usually suffer from complex non-uniform degradation, which includes both global and local blurs.  ...  The visualized feature maps of different branches indicated that our dual-branch network can decouple the global and local blur features efficiently.  ...  In order to adaptively restore different kinds of blur in the network, this paper disentangles the real complex blur image into near uniform global blur and non-uniform local blur.  ... 
doi:10.3390/app11052174 doaj:713be03e804246adaa667bfb09bed897 fatcat:cq4bwlqgerazzkb5cd57t76hre

Distributed localization algorithm for wireless sensor networks using range lookup and subregion stitching

Farhan Khan, Sing Kiong Nguang
2021 IET Wireless Sensor Systems  
Simulation results on uniform as well as irregular networks of various sizes show that the proposed algorithm provides improved localization accuracy and reduces localization error up to 25% in comparison  ...  Distributed localization algorithm for wireless sensor networks using range lookup and subregion stitching.  ...  The 32 nodes indoor uniform network provided a localization error of 1.2496 and the 32 nodes indoor irregular network provided a localization error of 2.9924.  ... 
doi:10.1049/wss2.12020 fatcat:7tt3fxqxrrbkrpbt5g2kegux24

Design and evaluation of a hierarchical on-chip interconnect for next-generation CMPs

Reetuparna Das, Soumya Eachempati, Asit K. Mishra, Vijaykrishnan Narayanan, Chita R. Das
2009 2009 IEEE 15th International Symposium on High Performance Computer Architecture  
and non-uniform synthetic traffic.  ...  The local network is a simple, high-bandwidth, low-power shared bus fabric, and the global network is a low-radix mesh.  ...  for uniform and non-uniform traffic patterns and all network sizes.  ... 
doi:10.1109/hpca.2009.4798252 dblp:conf/hpca/DasEMVD09 fatcat:5r7vomk5p5fgbe5fqqotrkizvy

Point Cloud Upsampling via Disentangled Refinement [article]

Ruihui Li, Xianzhi Li, Pheng-Ann Heng, Chi-Wing Fu
2021 arXiv   pre-print
Point clouds produced by 3D scanning are often sparse, non-uniform, and noisy.  ...  Specifically, we design a pair of local and global refinement units in the spatial refiner to evolve a coarse feature map.  ...  At present, Q may still be non-uniform and noisy like P, as illustrated in the figure's toy example.  ... 
arXiv:2106.04779v1 fatcat:d2w55ivbnrbb3cb5hp3jv2bvxa

Deep Networks for Human Visual Attention: A Hybrid Model Using Foveal Vision [chapter]

Ana Filipa Almeida, Rui Figueiredo, Alexandre Bernardino, José Santos-Victor
2017 Advances in Intelligent Systems and Computing  
and localization task saturates.  ...  The main contribution of our work lies in the evaluation of the performances obtained with different non-uniform resolutions.  ...  Finally, it would also be interesting to train the system directly with blur (uniform and non-uniform foveal).  ... 
doi:10.1007/978-3-319-70836-2_10 fatcat:qpfvushgnra77elwkzbj5cnkbe

Attention Network for Non-Uniform Deblurring

Qing Qi, Jichang Guo, Weipei Jin
2020 IEEE Access  
INDEX TERMS Generative adversarial networks, non-uniform image deblurring, attention network.  ...  Instead of relying on local receptive fields to construct features by previous state-of-the-art methods, the non-local features for capturing long-range dependencies and the local features rely on receptive  ...  [27] enlarge the receptive fields by developing the feature pyramid network. The method [27] merely relies on the local features and ignores long-range dependencies from the non-local features.  ... 
doi:10.1109/access.2020.2997408 fatcat:oyis2k6zx5bvxembvkibpc7f5q

NuI-Go: Recursive Non-Local Encoder-Decoder Network for Retinal Image Non-Uniform Illumination Removal [article]

Chongyi Li, Huazhu Fu, Runmin Cong, Zechao Li, Qianqian Xu
2020 arXiv   pre-print
analysis.To address this issue, we propose a non-uniform illumination removal network for retinal image, called NuI-Go, which consists of three Recursive Non-local Encoder-Decoder Residual Blocks (NEDRBs  ...  One of the most challenging quality degradation issues in retinal images is non-uniform which hinders the pathological information and further impairs the diagnosis of ophthalmologists and computer-aided  ...  local and non-local information simultaneously. • Benefiting from novel network architecture and physical model-based non-uniform illumination synthesis strategy, our method achieves impressive performance  ... 
arXiv:2008.02984v1 fatcat:yf77vmdebzhtzdwlnnz6lcvws4

On the stability of topological order in tensor network states [article]

Dominic J. Williamson, Clement Delcamp, Frank Verstraete, Norbert Schuch
2020 arXiv   pre-print
We construct a tensor network representation of the 3d toric code ground state that is stable to all local tensor perturbations, including those that do not map to local operators on the physical Hilbert  ...  The stability is established by mapping the phase diagram of the perturbed tensor network to that of the 3d Ising gauge theory, which has a non-zero finite temperature transition.  ...  We construct a tensor network representation of the 3d toric code ground state that is stable to a generating set of uniform local tensor perturbations, including those that do not map to local operators  ... 
arXiv:2012.15346v1 fatcat:vfgkqa4udbenzhrg3qlfus7ole

Non Uniform On Chip Power Delivery Network Synthesis Methodology [article]

Patrick Benediktsson, Jon A. Flandrin, Chen Zheng
2017 arXiv   pre-print
Congestion map is obtained based global route congestion estimation. A self-adaptive non-uniform PDN synthesis is then performed to globally and locally optimize PDN over selected regions.  ...  In this paper, we proposed a non-uniform power delivery network (PDN) synthesis methodology. It first constructs initial PDN using uniform approach.  ...  As power deliver network has become more and more challenge to design and close power integrity as well as save sufficient space for routing, we believe there are more optimization space for non-uniform  ... 
arXiv:1711.00425v3 fatcat:nrt6kp7v4bbqpant5ifv6un22u

Deep CNNs with Robust LBP Guiding Pooling for Face Recognition

Zhongjian Ma, Yuanyuan Ding, Baoqing Li, Xiaobing Yuan
2018 Sensors  
To address this issue, a robust Local Binary Pattern (LBP) Guiding Pooling (G-RLBP) mechanism is proposed in this paper to down sample the input feature maps and lower the noise impact simultaneously.  ...  Pooling layer in Convolutional Neural Networks (CNNs) is designed to reduce dimensions and computational complexity.  ...  Interest: The authors declare no conflict of interest.The founding sponsors had no role in the design of the study; in the collection, analyses, or interpretation of data; in the writing of the manuscript, and  ... 
doi:10.3390/s18113876 pmid:30423850 fatcat:2yl4pf4dkndxda5h4bz46c5lna
« Previous Showing results 1 — 15 out of 282,161 results